Global dynamics in neuro symbolic integration using energy minimization in mean field theory

Logic program and neural networks are two important aspects in artificial intelligence. This thesis is part of an endeavour towards neural networks and logic programming integration. The goal in performing logic programming based on the energy minimization scheme is to achieve the best ratio of glo...

Full description

Saved in:
Bibliographic Details
Format: Thesis
Language:English
Subjects:
Online Access:http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77974/1/Page%201-24.pdf
http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77974/2/Full%20text.pdf
http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77974/4/Muraly.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-unimap-77974
record_format uketd_dc
spelling my-unimap-779742023-03-06T00:51:32Z Global dynamics in neuro symbolic integration using energy minimization in mean field theory Zainor Ridzuan, Yahya. Dr. Logic program and neural networks are two important aspects in artificial intelligence. This thesis is part of an endeavour towards neural networks and logic programming integration. The goal in performing logic programming based on the energy minimization scheme is to achieve the best ratio of global minimum. However, there is no guarantee to find the best minimum in the network. To achieve this, a learning algorithm based on the Boltzmann Machine (BM) concept and Hyperbolic Tangent Activation Function (HTAF) was derived to accelerate the performance of doing logic programming in Hopfield Neural Network (HNN) by using Mean Field Theory (MFT). Logic programming for lower order (up to third order clauses) and higher order clauses (up to eight order clauses) have been developed for MFT. The performance of this method is compared with the existing methods of doing logic programming in HNN (BM and HTAF). The global minima ratio, hamming distances and computational time were used to measure the effectiveness of the proposed method. Then, Agent Based Models (ABM) were developed by using Netlogo. ABM can allow rapid development of models, easy addition of features and a user-friendly handling and coding. Later the developed models are tested by using real life and simulated data sets. The simulation results obtain agreed with the proposed learning algorithm. The performance of doing logic programming using MFT proved to be better than the BM and HTAF. Universiti Malaysia Perlis (UniMAP) Thesis en http://dspace.unimap.edu.my:80/xmlui/handle/123456789/77974 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77974/3/license.txt 8a4605be74aa9ea9d79846c1fba20a33 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77974/1/Page%201-24.pdf 9a03d219521607082de9857904548cfc http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77974/2/Full%20text.pdf 1acfa6dc5717b47ad80619772a805554 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77974/4/Muraly.pdf 33e49b9db65b06df92515a30dcc5e6b3 Universiti Malaysia Perlis (UniMAP) Logic programming Neural networks (Computer science) Mean Field Theory (MFT) Institute of Engineering Mathematics
institution Universiti Malaysia Perlis
collection UniMAP Institutional Repository
language English
advisor Zainor Ridzuan, Yahya. Dr.
topic Logic programming
Neural networks (Computer science)
Mean Field Theory (MFT)
spellingShingle Logic programming
Neural networks (Computer science)
Mean Field Theory (MFT)
Global dynamics in neuro symbolic integration using energy minimization in mean field theory
description Logic program and neural networks are two important aspects in artificial intelligence. This thesis is part of an endeavour towards neural networks and logic programming integration. The goal in performing logic programming based on the energy minimization scheme is to achieve the best ratio of global minimum. However, there is no guarantee to find the best minimum in the network. To achieve this, a learning algorithm based on the Boltzmann Machine (BM) concept and Hyperbolic Tangent Activation Function (HTAF) was derived to accelerate the performance of doing logic programming in Hopfield Neural Network (HNN) by using Mean Field Theory (MFT). Logic programming for lower order (up to third order clauses) and higher order clauses (up to eight order clauses) have been developed for MFT. The performance of this method is compared with the existing methods of doing logic programming in HNN (BM and HTAF). The global minima ratio, hamming distances and computational time were used to measure the effectiveness of the proposed method. Then, Agent Based Models (ABM) were developed by using Netlogo. ABM can allow rapid development of models, easy addition of features and a user-friendly handling and coding. Later the developed models are tested by using real life and simulated data sets. The simulation results obtain agreed with the proposed learning algorithm. The performance of doing logic programming using MFT proved to be better than the BM and HTAF.
format Thesis
title Global dynamics in neuro symbolic integration using energy minimization in mean field theory
title_short Global dynamics in neuro symbolic integration using energy minimization in mean field theory
title_full Global dynamics in neuro symbolic integration using energy minimization in mean field theory
title_fullStr Global dynamics in neuro symbolic integration using energy minimization in mean field theory
title_full_unstemmed Global dynamics in neuro symbolic integration using energy minimization in mean field theory
title_sort global dynamics in neuro symbolic integration using energy minimization in mean field theory
granting_institution Universiti Malaysia Perlis (UniMAP)
granting_department Institute of Engineering Mathematics
url http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77974/1/Page%201-24.pdf
http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77974/2/Full%20text.pdf
http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/77974/4/Muraly.pdf
_version_ 1776104237754744832